3423: Add min and max facet stats r=dureuill a=dureuill

# Pull Request

## Related issue
Fixes #3426

## What does this PR do?

### User standpoint

- When using a `facets` parameter in search, the facets that have numeric values are displayed in a new section of the response called `facetStats` that contains, per facet, the numeric min and max value of the hits returned by the search.

<details>
<summary>
Sample request/response
</summary>

```json
❯ curl \
  -X POST 'http://localhost:7700/indexes/meteorites/search?facets=mass' \
  -H 'Content-Type: application/json' \
  --data-binary '{ "q": "LL6", "facets":["mass", "recclass"], "limit": 5 }' | jsonxf
{
  "hits": [
    {
      "name": "Niger (LL6)",
      "id": "16975",
      "nametype": "Valid",
      "recclass": "LL6",
      "mass": 3.3,
      "fall": "Fell"
    },
    {
      "name": "Appley Bridge",
      "id": "2318",
      "nametype": "Valid",
      "recclass": "LL6",
      "mass": 15000,
      "fall": "Fell",
      "_geo": {
        "lat": 53.58333,
        "lng": -2.71667
      }
    },
    {
      "name": "Athens",
      "id": "4885",
      "nametype": "Valid",
      "recclass": "LL6",
      "mass": 265,
      "fall": "Fell",
      "_geo": {
        "lat": 34.75,
        "lng": -87.0
      }
    },
    {
      "name": "Bandong",
      "id": "4935",
      "nametype": "Valid",
      "recclass": "LL6",
      "mass": 11500,
      "fall": "Fell",
      "_geo": {
        "lat": -6.91667,
        "lng": 107.6
      }
    },
    {
      "name": "Benguerir",
      "id": "30443",
      "nametype": "Valid",
      "recclass": "LL6",
      "mass": 25000,
      "fall": "Fell",
      "_geo": {
        "lat": 32.25,
        "lng": -8.15
      }
    }
  ],
  "query": "LL6",
  "processingTimeMs": 15,
  "limit": 5,
  "offset": 0,
  "estimatedTotalHits": 42,
  "facetDistribution": {
    "mass": {
      "110000": 1,
      "11500": 1,
      "1161": 1,
      "12000": 1,
      "1215.5": 1,
      "127000": 1,
      "15000": 1,
      "1676": 1,
      "1700": 1,
      "1710.5": 1,
      "18000": 1,
      "19000": 1,
      "220000": 1,
      "2220": 1,
      "22300": 1,
      "25000": 2,
      "265": 1,
      "271000": 1,
      "2840": 1,
      "3.3": 1,
      "3000": 1,
      "303": 1,
      "32000": 1,
      "34000": 1,
      "36.1": 1,
      "45000": 1,
      "460": 1,
      "478": 1,
      "483": 1,
      "5500": 2,
      "600": 1,
      "6000": 1,
      "67.8": 1,
      "678": 1,
      "680.5": 1,
      "6930": 1,
      "8": 1,
      "8300": 1,
      "840": 1,
      "8400": 1
    },
    "recclass": {
      "L/LL6": 3,
      "LL6": 39
    }
  },
  "facetStats": {
    "mass": {
      "min": 3.3,
      "max": 271000.0
    }
  }
}
```

</details>

## PR checklist
Please check if your PR fulfills the following requirements:
- [ ] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)?
- [ ] Have you read the contributing guidelines?
- [ ] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


Co-authored-by: Louis Dureuil <louis@meilisearch.com>
This commit is contained in:
bors[bot] 2023-02-22 13:06:43 +00:00 committed by GitHub
commit ac5a1e4c4b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 368 additions and 42 deletions

View file

@ -108,7 +108,7 @@ pub struct SearchHit {
pub matches_position: Option<MatchesPosition>,
}
#[derive(Serialize, Debug, Clone, PartialEq, Eq)]
#[derive(Serialize, Debug, Clone, PartialEq)]
#[serde(rename_all = "camelCase")]
pub struct SearchResult {
pub hits: Vec<SearchHit>,
@ -118,6 +118,8 @@ pub struct SearchResult {
pub hits_info: HitsInfo,
#[serde(skip_serializing_if = "Option::is_none")]
pub facet_distribution: Option<BTreeMap<String, BTreeMap<String, u64>>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub facet_stats: Option<BTreeMap<String, FacetStats>>,
}
#[derive(Serialize, Debug, Clone, PartialEq, Eq)]
@ -129,6 +131,12 @@ pub enum HitsInfo {
OffsetLimit { limit: usize, offset: usize, estimated_total_hits: usize },
}
#[derive(Serialize, Debug, Clone, PartialEq)]
pub struct FacetStats {
pub min: f64,
pub max: f64,
}
pub fn perform_search(
index: &Index,
query: SearchQuery,
@ -300,7 +308,7 @@ pub fn perform_search(
HitsInfo::OffsetLimit { limit: query.limit, offset, estimated_total_hits: number_of_hits }
};
let facet_distribution = match query.facets {
let (facet_distribution, facet_stats) = match query.facets {
Some(ref fields) => {
let mut facet_distribution = index.facets_distribution(&rtxn);
@ -314,18 +322,23 @@ pub fn perform_search(
facet_distribution.facets(fields);
}
let distribution = facet_distribution.candidates(candidates).execute()?;
Some(distribution)
let stats = facet_distribution.compute_stats()?;
(Some(distribution), Some(stats))
}
None => None,
None => (None, None),
};
let facet_stats = facet_stats.map(|stats| {
stats.into_iter().map(|(k, (min, max))| (k, FacetStats { min, max })).collect()
});
let result = SearchResult {
hits: documents,
hits_info,
query: query.q.clone().unwrap_or_default(),
processing_time_ms: before_search.elapsed().as_millis(),
facet_distribution,
facet_stats,
};
Ok(result)
}